基于RFID电子车牌数据的公交行程时间预测方法
|
摘要
为了给公交优先信号配时系统提供足够的"思考"时间和准确的控制依据,基于重庆市RFID电子车牌数据提出了一种采用自适应渐消卡尔曼滤波和小波神经网络组合模型动态预测公交行程时间的方法。综合分析公交行程时间的动态和静态影响因素,选取的模型输入参量为标准车流量、路段车辆平均行程时间、平均车速离散性和前班次公交行程时间。利用RFID电子车牌系统采集重庆市鹅公岩大桥路段车辆行驶数据,选取3 000组实际运行数据完成公交行程时间预测模型的训练,另筛选50组数据验证模型的有效性和准确性。研究结果表明:组合模型可动态自适应预测公交行程时间,预测值平均相对误差为3.23%,绝对误差集中在8 s左右,明显优于2种单一模型和基于传统GPS数据的公交行程时间预测模型,可认为选择RFID电子车牌数据作为组合模型的输入,能够明显改善模型预测精度;组合模型预测值的残差分布更为集中、鲁棒性较好,泛化能力强。选择平均绝对误差值、均方根误差值和平均绝对百分比误差作为模型评价指标,结果进一步表明,组合模型的综合预测效果明显优于单一的自适应渐消卡尔曼滤波和小波神经网络。研究方案可为先进公交信息化系统提供良好的技术支撑。
To provide sufficient "thinking" time and accurate control for a transit signal priority(TSP) timing system, this study proposed a method that combines an adaptive fading Kalman filter and wavelet neural network to predict bus travel times dynamically. This is based on the Chongqing radio frequency identification(RFID) electronic license plate data. This study comprehensively analyzed the dynamic and static influencing factors of bus travel times and used the following model input parameters: standard traffic volume, average travel time over the road segment, average vehicle speed dispersion, and travel time of a pre-class bus. The RFID electronic license plate system was used to collect vehicle driving data of Chongqing Egongyan Bridge and the bus travel time prediction model was trained using 3 000 sets of actual operational data. Fifty groups of actual running data were used to verify the validity and accuracy of the model. Experimental results show that the combination model can dynamically and adaptively predict bus travel times. The average relative error of the predicted value is 3.23%, whereas the absolute error is approximately 8 s. These errors are obviously better than those of the two previous single models and the travel time prediction model based on traditional GPS data. This study shows that selecting RFID vehicle license plate data as input for the combination model can significantly improve the model's prediction accuracy. The residuals distribution is more concentrated in the combination model, which has good robustness and a strong generalization ability. The mean absolute error, root mean square percentage error, and mean absolute percentage error were selected as model evaluation indicators. Comprehensive prediction capabilities of the combination model are obviously better than that of both the single fading Kalman filter and wavelet neural network. This research can provide effective technical support for advanced public transportation information systems.
To provide sufficient "thinking" time and accurate control for a transit signal priority(TSP) timing system, this study proposed a method that combines an adaptive fading Kalman filter and wavelet neural network to predict bus travel times dynamically. This is based on the Chongqing radio frequency identification(RFID) electronic license plate data. This study comprehensively analyzed the dynamic and static influencing factors of bus travel times and used the following model input parameters: standard traffic volume, average travel time over the road segment, average vehicle speed dispersion, and travel time of a pre-class bus. The RFID electronic license plate system was used to collect vehicle driving data of Chongqing Egongyan Bridge and the bus travel time prediction model was trained using 3 000 sets of actual operational data. Fifty groups of actual running data were used to verify the validity and accuracy of the model. Experimental results show that the combination model can dynamically and adaptively predict bus travel times. The average relative error of the predicted value is 3.23%, whereas the absolute error is approximately 8 s. These errors are obviously better than those of the two previous single models and the travel time prediction model based on traditional GPS data. This study shows that selecting RFID vehicle license plate data as input for the combination model can significantly improve the model's prediction accuracy. The residuals distribution is more concentrated in the combination model, which has good robustness and a strong generalization ability. The mean absolute error, root mean square percentage error, and mean absolute percentage error were selected as model evaluation indicators. Comprehensive prediction capabilities of the combination model are obviously better than that of both the single fading Kalman filter and wavelet neural network. This research can provide effective technical support for advanced public transportation information systems.
引文
[1]ZHOU T,SUN D H,ZHAO M,et al.Feedback Control Scheme of Traffic Jams Based on the Coupled Map Car-following Model[J].Chinese Physics B,2013,22(9):203-208.
[2]王健,曹阳,王运豪.考虑出行时间窗的定制公交线路车辆调度方法[J].中国公路学报,2018,31(5):143-150.WANG Jian,CAO Yang,WANG Yun-hao.Customized Bus Route Vehicle Schedule Method Considering Travel Time Windows[J].China Journal of Highway and Transport,2018,31(5):143-150.
[3]向红艳,彭学文.公交到站时间预测研究现状与发展趋势[J].交通信息与安全,2014,32(4):57-61.XIANG Hong-yan,PENG Xue-wen.Current Study and Development Trend of Bus Arrival Time Prediction[J].Journal of Transport Information and Safety,2014,32(4):57-61.
[4]刘昱岗,王卓君,潘璐,等.公交车辆检测及其行程时间预测[J].中国公路学报,2016,29(10):95-104.LIU Yu-gang,WANG Zhuo-jun,PAN Lu,et al.Bus Detection and Its Travel Time Prediction[J].China Journal of Highway and Transport,2016,29(10):95-104.
[5]CHEN G J,YANG X G,ZHANG D.Bus Arrival Time Prediction Models:Link Based and Section Based[J].Journal of Transportation Engineering,2012,138(1):60-66.
[6]BIRR K,JAMROZ K,KUSTRA W.Travel Time of Public Transport Vehicles Estimation[J].Transportation Research Procedia,2014(3):359-365.
[7]孙喜梅,杨兆升.城市公共交通站点间实时动态行程时间预测的模型[J].吉林大学学报:工学版,2002,32(1):47-51.SUN Xi-mei,YANG Zhao-sheng.A Dynamic Real Time Prediction Model of Urban Public Transport’s Travel Time Between Stations[J].Journal of University:Engineering and Technology Edition,2002,32(1):47-51.
[8]PATNAIK J,CHIEN S,BLADIKAS A.Estimation of Bus Arrival Times Using APC Data[J].Physical Review Letters,2004,7(1):128001-128100.
[9]SONG X H,TENG J,CHEN G J,et al.Predicting Bus Real-time Travel Time Basing on Both GPS and RFID Data[J].Procedia-Social and Behavioral Sciences,2013,96:2287-2299.
[10]周文霞,徐建闽,刘正东.基于卡尔曼滤波算法的公交车辆行程时间预测[J].交通标准化,2007(2):174-177.ZHOU Wen-xia,XU Jian-min,LIU Zheng-dong.Forecasting of Travel Time for Public Transport Vehicles Based on the Kalman Filtering Algorithm[J].Communications Standardization,2007(2):174-177.
[11]ELHENAWY M,CHEN H,RAKHA H A.Dynamic Travel Time Prediction Using Data Clustering and Genetic Programming[J].Transportation Research Part C,2014,42(42):82-98.
[12]CHEN M,YAW J,CHIEN S I,et al.Using Automatic Passenger Counter Data in Bus Arrival Time Prediction[J].Journal of Advanced Transportation,2007,41(3):267-283.
[13]YING T,ZHONG G,ZHANG J,et al.A Prediction Model of Bus Arrival Time at Stops with Multiroutes[J].Transportation Research Procedia,2017,25:4627-4640.
[14]XIN J X,CHEN S Y.Bus Dwell Time Prediction Based on KNN[J].Procedia Engineering,2016,137:283-288.
[15]陈旭梅,龚辉波,王景楠.基于SVM和Kalman滤波的BRT行程时间预测模型研究[J].交通运输系统工程与信息,2012,12(4):29-34.CHEN Xu-mei,GONG Hui-bo,WANG Jing-nan.Research on BRT Travel Time Prediction Model Based on SVM and Kalman Filtering[J].Transportation System Engineering and Information,2012,12(4):29-34.
[16]AMITA J,JAIN S S,GARG P K.Prediction of Bus Travel Time Using ANN:A Case Study in Delhi[J].Transportation Research Procedia,2016,17:263-272.
[17]JENELIUS E,KOUTSOPOULOS H N.Travel Time Estimation for Urban Road Networks Using Low Frequency Probe Vehicle Data[J].Transportation Research Part B,2013,53(4):64-81.
[18]任远,吕永波,马继辉,等.基于粒子滤波的公交车辆到站时间预测研究[J].交通运输系统工程与信息,2016,16(6):142-146.REN Yuan,LV Yong-bo,Ma Ji-hui,et al.Bus Arrival Time Prediction Based on Particle Filter[J].Journal of Transportation Systems Engineering and Information Technology,2016,16(6):142-146.
[19]李梦妍,于文震.基于改进小波神经网络和灰色模型的装备性能参数预测[J].电子测量技术,2016,39(3):18-22.LI Meng-yan,YU Wen-zhen.Prediction of Equipment Performance Parameters Based on Improved Wavelet Neural Network and Grey Model[J].Electronic Measurement Technology,2016,39(3):18-22.
[20]秦鸣,杨高飞,邓明君,等.基于二次指数平滑法和优化Kalman滤波的短时交通组合预测[J].北华大学学报:自然科学版,2015,16(6):814-817.QIN Ming,YANG Gao-fei,DENG Ming-jun,et al.Short Time Traffic Combination Forecast Based on Two Exponential Smoothing and Optimized Kalman Filtering[J].Journal of Beihua University:Natural Science,2015,16(6):814-817.
[21]陈曦.考虑速度离散特性的高速公路交通状态估计方法研究[D].重庆:重庆大学,2016.CHEN Xi.Study on Freeway Traffic State Estimation Method Considering Speed Difference Characteristics[D].Chongqing:Chongqing University,2016.
[22]季彦婕,陆佳炜,陈晓实,等.基于粒子群小波神经网络的公交到站时间预测[J].交通运输系统工程与信息,2016,16(3):60-66.JI Yan-jie,LU Jia-wei,CHEN Xiao-shi,et al.Prediction of Bus Arrival Time Based on Particle Swarm Optimization(PSO)Wavelet Neural Network[J].Journal of Transportation Systems Engineering and Information Technology,2016,16(3):60-66.
[23]YU Z,WOOD J S,GAYAH V V.Using Survival Models to Estimate Bus Travel Times and Associated Uncertainties[J].Transportation Research Part C,2017,74:366-382.
[24]许伦辉,傅惠.交通信息智能预测理论与方法[M].北京:科学出版社,2009.XU Lun-hui,FU Hui.Theory and Method of Intelligent Traffic Information Prediction[M].Beijing:Science Press,2009.
[25]计晓昕,关伟.组合非参数回归和卡尔曼滤波的公交车到站时间预测[J].科学技术与工程,2013,13(32):9581-9586.JI Xiao-xin,GUAN Wei.Prediction of Bus Arrival Time by Combined Nonparametric Regression and Kalman Filtering[J].Science Technology and Engineering,2013,13(32):9581-9586.
[26]柏丛,彭仲仁.基于动态模型的公交车行程时间预测[J].计算机工程与应用,2016,52(3):103-107.BAI Cong,PENG Zhong-ren.Bus Travel Time Prediction Based on Dynamic Model[J].Computer Engineering and Applications,2016,52(3):103-107.
[2]王健,曹阳,王运豪.考虑出行时间窗的定制公交线路车辆调度方法[J].中国公路学报,2018,31(5):143-150.WANG Jian,CAO Yang,WANG Yun-hao.Customized Bus Route Vehicle Schedule Method Considering Travel Time Windows[J].China Journal of Highway and Transport,2018,31(5):143-150.
[3]向红艳,彭学文.公交到站时间预测研究现状与发展趋势[J].交通信息与安全,2014,32(4):57-61.XIANG Hong-yan,PENG Xue-wen.Current Study and Development Trend of Bus Arrival Time Prediction[J].Journal of Transport Information and Safety,2014,32(4):57-61.
[4]刘昱岗,王卓君,潘璐,等.公交车辆检测及其行程时间预测[J].中国公路学报,2016,29(10):95-104.LIU Yu-gang,WANG Zhuo-jun,PAN Lu,et al.Bus Detection and Its Travel Time Prediction[J].China Journal of Highway and Transport,2016,29(10):95-104.
[5]CHEN G J,YANG X G,ZHANG D.Bus Arrival Time Prediction Models:Link Based and Section Based[J].Journal of Transportation Engineering,2012,138(1):60-66.
[6]BIRR K,JAMROZ K,KUSTRA W.Travel Time of Public Transport Vehicles Estimation[J].Transportation Research Procedia,2014(3):359-365.
[7]孙喜梅,杨兆升.城市公共交通站点间实时动态行程时间预测的模型[J].吉林大学学报:工学版,2002,32(1):47-51.SUN Xi-mei,YANG Zhao-sheng.A Dynamic Real Time Prediction Model of Urban Public Transport’s Travel Time Between Stations[J].Journal of University:Engineering and Technology Edition,2002,32(1):47-51.
[8]PATNAIK J,CHIEN S,BLADIKAS A.Estimation of Bus Arrival Times Using APC Data[J].Physical Review Letters,2004,7(1):128001-128100.
[9]SONG X H,TENG J,CHEN G J,et al.Predicting Bus Real-time Travel Time Basing on Both GPS and RFID Data[J].Procedia-Social and Behavioral Sciences,2013,96:2287-2299.
[10]周文霞,徐建闽,刘正东.基于卡尔曼滤波算法的公交车辆行程时间预测[J].交通标准化,2007(2):174-177.ZHOU Wen-xia,XU Jian-min,LIU Zheng-dong.Forecasting of Travel Time for Public Transport Vehicles Based on the Kalman Filtering Algorithm[J].Communications Standardization,2007(2):174-177.
[11]ELHENAWY M,CHEN H,RAKHA H A.Dynamic Travel Time Prediction Using Data Clustering and Genetic Programming[J].Transportation Research Part C,2014,42(42):82-98.
[12]CHEN M,YAW J,CHIEN S I,et al.Using Automatic Passenger Counter Data in Bus Arrival Time Prediction[J].Journal of Advanced Transportation,2007,41(3):267-283.
[13]YING T,ZHONG G,ZHANG J,et al.A Prediction Model of Bus Arrival Time at Stops with Multiroutes[J].Transportation Research Procedia,2017,25:4627-4640.
[14]XIN J X,CHEN S Y.Bus Dwell Time Prediction Based on KNN[J].Procedia Engineering,2016,137:283-288.
[15]陈旭梅,龚辉波,王景楠.基于SVM和Kalman滤波的BRT行程时间预测模型研究[J].交通运输系统工程与信息,2012,12(4):29-34.CHEN Xu-mei,GONG Hui-bo,WANG Jing-nan.Research on BRT Travel Time Prediction Model Based on SVM and Kalman Filtering[J].Transportation System Engineering and Information,2012,12(4):29-34.
[16]AMITA J,JAIN S S,GARG P K.Prediction of Bus Travel Time Using ANN:A Case Study in Delhi[J].Transportation Research Procedia,2016,17:263-272.
[17]JENELIUS E,KOUTSOPOULOS H N.Travel Time Estimation for Urban Road Networks Using Low Frequency Probe Vehicle Data[J].Transportation Research Part B,2013,53(4):64-81.
[18]任远,吕永波,马继辉,等.基于粒子滤波的公交车辆到站时间预测研究[J].交通运输系统工程与信息,2016,16(6):142-146.REN Yuan,LV Yong-bo,Ma Ji-hui,et al.Bus Arrival Time Prediction Based on Particle Filter[J].Journal of Transportation Systems Engineering and Information Technology,2016,16(6):142-146.
[19]李梦妍,于文震.基于改进小波神经网络和灰色模型的装备性能参数预测[J].电子测量技术,2016,39(3):18-22.LI Meng-yan,YU Wen-zhen.Prediction of Equipment Performance Parameters Based on Improved Wavelet Neural Network and Grey Model[J].Electronic Measurement Technology,2016,39(3):18-22.
[20]秦鸣,杨高飞,邓明君,等.基于二次指数平滑法和优化Kalman滤波的短时交通组合预测[J].北华大学学报:自然科学版,2015,16(6):814-817.QIN Ming,YANG Gao-fei,DENG Ming-jun,et al.Short Time Traffic Combination Forecast Based on Two Exponential Smoothing and Optimized Kalman Filtering[J].Journal of Beihua University:Natural Science,2015,16(6):814-817.
[21]陈曦.考虑速度离散特性的高速公路交通状态估计方法研究[D].重庆:重庆大学,2016.CHEN Xi.Study on Freeway Traffic State Estimation Method Considering Speed Difference Characteristics[D].Chongqing:Chongqing University,2016.
[22]季彦婕,陆佳炜,陈晓实,等.基于粒子群小波神经网络的公交到站时间预测[J].交通运输系统工程与信息,2016,16(3):60-66.JI Yan-jie,LU Jia-wei,CHEN Xiao-shi,et al.Prediction of Bus Arrival Time Based on Particle Swarm Optimization(PSO)Wavelet Neural Network[J].Journal of Transportation Systems Engineering and Information Technology,2016,16(3):60-66.
[23]YU Z,WOOD J S,GAYAH V V.Using Survival Models to Estimate Bus Travel Times and Associated Uncertainties[J].Transportation Research Part C,2017,74:366-382.
[24]许伦辉,傅惠.交通信息智能预测理论与方法[M].北京:科学出版社,2009.XU Lun-hui,FU Hui.Theory and Method of Intelligent Traffic Information Prediction[M].Beijing:Science Press,2009.
[25]计晓昕,关伟.组合非参数回归和卡尔曼滤波的公交车到站时间预测[J].科学技术与工程,2013,13(32):9581-9586.JI Xiao-xin,GUAN Wei.Prediction of Bus Arrival Time by Combined Nonparametric Regression and Kalman Filtering[J].Science Technology and Engineering,2013,13(32):9581-9586.
[26]柏丛,彭仲仁.基于动态模型的公交车行程时间预测[J].计算机工程与应用,2016,52(3):103-107.BAI Cong,PENG Zhong-ren.Bus Travel Time Prediction Based on Dynamic Model[J].Computer Engineering and Applications,2016,52(3):103-107.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |